{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/g-daug-generative-data-augmentation-for","title":"Generative Data Augmentation for Commonsense Reasoning","arxiv_id":"2004.11546","date":"2020-04-24","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Yiben Yang","Chaitanya Malaviya","Jared Fernandez","Swabha Swayamdipta","Ronan Le Bras","Ji-Ping Wang","Chandra Bhagavatula","Yejin Choi","Doug Downey"],"abstract":"Recent advances in commonsense reasoning depend on large-scale human-annotated training data to achieve peak performance. However, manual curation of training examples is expensive and has been shown to introduce annotation artifacts that neural models can readily exploit and overfit on. We investigate G-DAUG^C, a novel generative data augmentation method that aims to achieve more accurate and robust learning in the low-resource setting. Our approach generates synthetic examples using pretrained language models, and selects the most informative and diverse set of examples for data augmentation. In experiments with multiple commonsense reasoning benchmarks, G-DAUG^C consistently outperforms existing data augmentation methods based on back-translation, and establishes a new state-of-the-art on WinoGrande, CODAH, and CommonsenseQA. Further, in addition to improvements in in-distribution accuracy, G-DAUG^C-augmented training also enhances out-of-distribution generalization, showing greater robustness against adversarial or perturbed examples. Our analysis demonstrates that G-DAUG^C produces a diverse set of fluent training examples, and that its selection and training approaches are important for performance. Our findings encourage future research toward generative data augmentation to enhance both in-distribution learning and out-of-distribution generalization.","url_abs":"https://arxiv.org/abs/2004.11546v3","url_pdf":"https://arxiv.org/pdf/2004.11546v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"g-daug-generative-data-augmentation-for","repo_url":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"coreference-resolution","task_name":"Coreference Resolution"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"out-of-distribution-generalization","task_name":"Out-of-Distribution Generalization"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"winogrande","task_name":"Winogrande"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"G-DAUG-Combo + RoBERTa-Large","rank_in_archive_order":35,"of":77,"metrics":{"Accuracy":"71.4"},"uses_additional_data":false},{"leaderboard":"/sota/coreference-resolution-on-winograd-schema","task":"Coreference Resolution","dataset":"Winograd Schema Challenge","model":"RoBERTa-large + G-DAug-Inf","rank_in_archive_order":22,"of":82,"metrics":{"Accuracy":"80"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-codah","task":"Question Answering","dataset":"CODAH","model":"G-DAUG-Combo + RoBERTa-Large","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"84.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.11546","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.11546"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","reach":null}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"0244bd3dbebdd14a","entry":"randargmin","repo":"yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","repo_kind":"official","path":"finetune_gd_swag.py","file_url":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning/blob/HEAD/finetune_gd_swag.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0244bd3dbebdd14a"}},{"code_sha256_prefix":"541fe035a87b91ca","entry":"top_k_top_p_filtering","repo":"yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","repo_kind":"official","path":"modeling.py","file_url":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning/blob/HEAD/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"541fe035a87b91ca"}},{"code_sha256_prefix":"56c5c1024fb026bd","entry":"select_field","repo":"yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","repo_kind":"official","path":"finetune_gd_swag.py","file_url":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning/blob/HEAD/finetune_gd_swag.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56c5c1024fb026bd"}},{"code_sha256_prefix":"3c241ecfe3749a6d","entry":"simple_accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3c241ecfe3749a6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}